gpt-oss 20B › NVIDIA Tesla V100 16GB
gpt-oss 20B on the NVIDIA Tesla V100 16GB
Best measured: 118 tokens/s generation and 3,527 tokens/s prompt processing (MXFP4, CUDA, FA on).
For comparison, our size-scaling estimate for this combination is 115 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| MXFP4 | CUDA FA on | 118 | 3,527 | tg128 | ggerganov llama-bench model column: gpt-oss 20B MXFP4 MoE | llama.cpp discussion #15396 |
tg128 = generating 128 tokens; pp512 = reading a 512-token prompt (llama-bench). LocalScore averages several prompt and output lengths, so its numbers run lower than tg128.
Rent one by the hour
Rent a GPU on RunPodAffiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.
All results for the NVIDIA Tesla V100 16GB · gpt-oss 20B on other hardware